Back to leaderboard

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Marginal

Jun 25, 2026 · Cortex-A78AE

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
46 vs 18
Hardware Fit
93 vs 53
Quality Score
26 vs 3

Hardware

gemma3:4b qwen3.5:0.8b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperLENOVO 20L7CTO1WW
CPUCortex-A78AEIntel Core™ i5-8350U
Cores68
RAM7 GB23 GB
GPUIntegrated / UnknownKaby Lake-R GT2 [UHD Graphics 620]
OSUbuntu 22.04.5 LTSFedora Linux 43
Archarm64x64
Power Modebalancedlow-power

Performance

gemma3:4b qwen3.5:0.8b
Tokens/sec14.99.4
First chunk2204 ms799 ms
TTFT2.2 s30.0 s
Load time2.0 s3.3 s
Memory usage2.6 GB1.9 GB
Memory %35%8%

HW Fit Score Breakdown

gemma3:4b

Speed
45/50
TTFT
19/20
Memory
29/30

qwen3.5:0.8b

Speed
23/50
TTFT
0/20
Memory
30/30

Quality

gemma3:4b

Reasoning
11/20
Coding
11/20
Instruction
0/20
Structured
0/15
Math
4/15
Multilingual
0/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Poor

qwen3.5:0.8b

Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View gemma3:4b details | View qwen3.5:0.8b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest